Cross-lingual and ensemble MLPs strategies for low-resource speech recognition

13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012

Volumn 3, Issue , 2012, Pages 2581-2584

  Qian, Yanmin ^a   Liu, Jia ^a  

^a TSINGHUA UNIVERSITY   (China)

Author keywords

Cross lingual posterior features; Ensemble system; Hierarchical architectures; Low resource language

Indexed keywords

ACOUSTIC FEATURES; ENSEMBLE SYSTEMS; HIERARCHICAL ARCHITECTURES; LOW-RESOURCE LANGUAGE; LOW-RESOURCE SPEECH RECOGNITION; POSTERIOR FEATURES; SOURCES OF INFORMATIONS; SYSTEM COMBINATION;

COMPUTER APPLICATIONS; COMPUTER SIMULATION;

SPEECH RECOGNITION;

EID: 84878582419     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: None     Document Type: Conference Paper

References (17)

1. P. Fung and T. Schultz, "Multilingual spoken language processing," IEEE Signal Processing Magazine, vol. 25, pp. 89-97, May. 2008.
2. X. Cui, J. Xue, et al., "Acoustic Modeling with Bootstrap and Restructuring for Low-Resourced Languages," in Proc. Of INTERSPEECH, pp:2974-2977, 2010.
3. B. D. Walker, B. C. Lackey, J. S. Muller, and P. J. Schone, "Language-Reconfigurable Universal Phone Recognition," in Proc. Of EUROSPEECH, 2003.
4. H. Lin, L. Deng, et al., "A Study on Multilingual Acoustic Modeling for Large Vocabulary ASR," in Proc. Of ICASSP, pp:4333-4336, 2009.
5. D. Povey, L. Burget, et al., "The Subspace Gaussian Mixture Model-A Structured Model for Speech Recognition," Computer Speech and Language, vol. 25, Issue 2, pp:404-439, 2011.
6. Y. Qian, D. Povey, J. Liu, "State-Level Data Borrowing for Low-Resource Speech Recognition based on Subspace GMMs," in Proc. Of INTERSPECH, 2011.
7. S. M. Siniscalchi, T. Svendsen, and C. H. Lee, "Toward A Detector-Based Universal Phone Recognizer," in Proc. Of ICASSP, pp:4261-4264, 2008.
8. Y. Qian, J. Xu, D. Povey, J. Liu, "Strategies for Using MLP based Features with Limited Target-Language Training Data," in Proc. Of ASRU, 2011.
9. S. Stuker, T. Schultz, F. Metze, and A. Waibel, "Multilingual articulatory features," in Proc. Of ICASSP, pp: 144-147, 2003.
10. S. Thomas, S. Ganapathy and H. Hermansky, "Crosslingual and Multi-stream Posterior Features for Low Resource LVCSR Systems," in Porc. Of INTERSPEECH, pp: 877-880, 2010.
11. Q. Zhu, B. Chen, N. Morgan and A. Stolcke, "On using MLP features in LVCSR," in Proc. Of INTERSPEECH, pp:921-924, 2004.
12. A. Stolcke et.al., "Cross-domain and cross-language portability of acoustic feature estimated by multilayer perceptrons," in Proc. Of ICASSP, pp: 321-324, 2006.
13. H. Hermansky, D.P.W. Ellis, and S. Sharma, "Tandem connectionist feature extraction for conventional HMM systems," in Proc. Of ICASSP, pp: 1635-1638, 2000.
14. J. Pinto, M. Magimai.-Doss, and H. Bourlard, "MLP Based Hierarchical System for Task Adaptation in ASR," in Proc. Of ASRU, 2009.
15. Yanmin Qian and Jia Liu, "Phone Modeling and Combining Discriminative Training for Mandarin-English Bilingual Speech Recognition", in Proc. Of ICASSP, pp:4918-4921, 2010.
16. X. Chen and Y. Zhao, "Data sampling ensemble acoustic modeling," in Proc. Of ICASSP, pp: 3805-3808, 2009.
17. ICSI QuickNet Software Package, http://www.icsi.Berkeley.deu/speech/qn. htm.